English
Related papers

Related papers: Last-Iterate Convergent Policy Gradient Primal-Dua…

200 papers

The problem of constrained Markov decision process is considered. An agent aims to maximize the expected accumulated discounted reward subject to multiple constraints on its costs (the number of constraints is relatively small). A new dual…

Optimization and Control · Mathematics 2022-10-21 Egor Gladin , Maksim Lavrik-Karmazin , Karina Zainullina , Varvara Rudenko , Alexander Gasnikov , Martin Takáč

Policy Mirror Descent (PMD) stands as a versatile algorithmic framework encompassing several seminal policy gradient algorithms such as natural policy gradient, with connections with state-of-the-art reinforcement learning (RL) algorithms…

Machine Learning · Computer Science 2024-11-07 Kimon Protopapas , Anas Barakat

Continuous time primal-dual gradient dynamics that find a saddle point of a Lagrangian of an optimization problem have been widely used in systems and control. While the global asymptotic stability of such dynamics has been well-studied, it…

Optimization and Control · Mathematics 2019-09-17 Guannan Qu , Na Li

In the Lasry--Lions framework, Mean-Field Games (MFGs) model interactions among an infinite number of agents. However, existing algorithms either require strict monotonicity or only guarantee the convergence of averaged iterates, as in…

Computer Science and Game Theory · Computer Science 2025-10-28 Noboru Isobe , Kenshi Abe , Kaito Ariu

In this paper, we present a new policy gradient (PG) methods, namely the block policy mirror descent (BPMD) method for solving a class of regularized reinforcement learning (RL) problems with (strongly)-convex regularizers. Compared to the…

Machine Learning · Computer Science 2022-09-20 Guanghui Lan , Yan Li , Tuo Zhao

This paper studies equality-constrained minimization problems through the lens of feedback control. We introduce a unified control-theoretic framework by showing that a PID feedback law acting on the dual variable induces the PID…

Optimization and Control · Mathematics 2026-04-13 Veronica Centorrino , Rawan Hoteit , Efe C. Balta , John Lygeros

This paper considers the decision-dependent optimization problem, where the data distributions react in response to decisions affecting both the objective function and linear constraints. We propose a new method termed repeated projected…

Optimization and Control · Mathematics 2025-08-13 Zifan Wang , Changxin Liu , Thomas Parisini , Michael M. Zavlanos , Karl H. Johansson

Efficient exploration is a central problem in reinforcement learning and is often formalized as maximizing the entropy of the state-action occupancy measure. While unconstrained maximum-entropy exploration is relatively well understood,…

Machine Learning · Computer Science 2026-05-01 Florian Wolf , Ilyas Fatkhullin , Niao He

Motivated by applications in Game Theory, Optimization, and Generative Adversarial Networks, recent work of Daskalakis et al \cite{DISZ17} and follow-up work of Liang and Stokes \cite{LiangS18} have established that a variant of the widely…

Optimization and Control · Mathematics 2025-09-30 Constantinos Daskalakis , Ioannis Panageas

Markov decision processes (MDPs) are used to model stochastic systems in many applications. Several efficient algorithms to compute optimal policies have been studied in the literature, including value iteration (VI) and policy iteration.…

Optimization and Control · Mathematics 2021-08-30 Vineet Goyal , Julien Grand-Clement

To overcome the curse of dimensionality and curse of modeling in Dynamic Programming (DP) methods for solving classical Markov Decision Process (MDP) problems, Reinforcement Learning (RL) algorithms are popular. In this paper, we consider…

Machine Learning · Computer Science 2018-11-29 Arghyadip Roy , Vivek Borkar , Abhay Karandikar , Prasanna Chaporkar

Direct policy gradient methods for reinforcement learning are a successful approach for a variety of reasons: they are model free, they directly optimize the performance metric of interest, and they allow for richly parameterized policies.…

Machine Learning · Computer Science 2020-08-14 Alekh Agarwal , Mikael Henaff , Sham Kakade , Wen Sun

We introduce two novel primal-dual algorithms for addressing nonconvex, nonconcave, and nonsmooth saddle point problems characterized by the weak Minty Variational Inequality (MVI). The first algorithm, Nonconvex-Nonconcave Primal-Dual…

Optimization and Control · Mathematics 2025-06-19 Iyad Walwil , Olivier Fercoq

In this paper we propose a primal-dual dynamical approach to the minimization of a structured convex function consisting of a smooth term, a nonsmooth term, and the composition of another nonsmooth term with a linear continuous operator. In…

Optimization and Control · Mathematics 2020-08-03 Radu Ioan Bot , Ernö Robert Csetnek , Szilard Laszlo

Safe Reinforcement Learning from Human Feedback (Safe RLHF) has recently achieved empirical success in developing helpful and harmless large language models by decoupling human preferences regarding helpfulness and harmlessness. Existing…

Machine Learning · Computer Science 2026-04-22 Qiang Liu , Adrienne Kline , Ermin Wei

The problem of constrained reinforcement learning (CRL) holds significant importance as it provides a framework for addressing critical safety satisfaction concerns in the field of reinforcement learning (RL). However, with the introduction…

Machine Learning · Computer Science 2023-05-24 Chengbin Xuan , Feng Zhang , Faliang Yin , Hak-Keung Lam

In this paper, we propose a unified primal-dual algorithm framework based on the augmented Lagrangian function for composite convex problems with conic inequality constraints. The new framework is highly versatile. First, it not only covers…

Optimization and Control · Mathematics 2022-08-31 Zhenyuan Zhu , Fan Chen , Junyu Zhang , Zaiwen Wen

The linear primal-dual hybrid gradient (PDHG) method is a first-order method that splits convex optimization problems with saddle-point structure into smaller subproblems. Unlike those obtained in most splitting methods, these subproblems…

Optimization and Control · Mathematics 2022-04-05 Jérôme Darbon , Gabriel P. Langlois

Stochastic gradient descent (SGD) is perhaps the most prevalent optimization method in modern machine learning. Contrary to the empirical practice of sampling from the datasets without replacement and with (possible) reshuffling at each…

Optimization and Control · Mathematics 2024-02-08 Xufeng Cai , Cheuk Yin Lin , Jelena Diakonikolas

In this paper, we present novel randomized algorithms for solving saddle point problems whose dual feasible region is given by the direct product of many convex sets. Our algorithms can achieve an ${\cal O}(1/N)$ and ${\cal O}(1/N^2)$ rate…

Optimization and Control · Mathematics 2015-11-16 Cong Dang , Guanghui Lan